© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 79072
    Prev
    Next
    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .linspace
    -0.07
     recently
    -0.07
     beacon
    -0.07
    .refresh
    -0.07
     atualmente
    -0.07
    flare
    -0.07
    note
    -0.07
     ingresso
    -0.07
     pathways
    -0.07
     fluctuations
    -0.07
    POSITIVE LOGITS
     preceding
    0.09
     Decorative
    0.08
     Rollen
    0.08
     menget
    0.08
     ಕೋಟ
    0.08
    เปอร์
    0.08
     multiplying
    0.08
     ટકા
    0.08
     Institution
    0.08
     %,
    0.08
    Activations Density 0.002%

    No Known Activations